Template-based prediction of vigilance fluctuations in resting-state fMRI

Abstract

Changes in vigilance or alertness during a typical resting state fMRI scan are inevitable and have been found to affect measures of functional brain connectivity. Since it is not often feasible to monitor vigilance with EEG during fMRI scans, it would be of great value to have methods for estimating vigilance levels from fMRI data alone. A recent study, conducted in macaque monkeys, proposed a template-based approach for fMRI-based estimation of vigilance fluctuations. Here, we use simultaneously acquired EEG/fMRI data to investigate whether the same template-based approach can be employed to estimate vigilance fluctuations of awake humans across different resting-state conditions. We first demonstrate that the spatial pattern of correlations between EEG-defined vigilance and fMRI in our data is consistent with the previous literature. Notably, however, we observed a significant difference between the eyes-closed (EC) and eyes-open (EO) conditions, finding stronger negative correlations with vigilance in regions forming the default mode network and higher positive correlations in thalamus and insula in the EC condition when compared to the EO condition. Taking these correlation maps as "templates" for vigilance estimation, we found that the template-based approach produced fMRI-based vigilance estimates that were significantly correlated with EEG-based vigilance measures, indicating its generalizability from macaques to humans. We also demonstrate that the performance of this method was related to the overall amount of variability in a subject's vigilance state, and that the template-based approach outperformed the use of the global signal as a vigilance estimator. In addition, we show that the template-based approach can be used to estimate the variability across scans in the amplitude of the vigilance fluctuations. We discuss the benefits and tradeoffs of using the template-based approach in future fMRI studies.

Keywords: Caffeine; Eyes-closed; Eyes-open; Global signal; Resting state fMRI; Simultaneous EEG-fMRI; Vigilance.

Figure 1:

Correlation between the EEG-based vigilance time series and the estimated vigilance using Temp_LOO across subjects and runs for the ECnonCaf scans on the top row and the EOnonCaf scans in the bottom row. (* p < 0.05)

Figure 2:

Left: Average of the correlation maps derived from all non caffeine scans, with EC on top and EO in bottom row; Middle: Average of the correlation maps derived from post caffeine session, with EC on top and EO in bottom row; Right: Spatial correlation between the average correlation maps derived from different conditions.

Figure 3:

Group result z-scores (from 3ttest++) showing areas of significant difference between the vigilance correlation maps derived from different sessions. The top row shows the ECnonCaf minus EOnonCaf map (p < 0.05, corrected). The middle and the bottom rows display preCaf minus postCaf for eyes-closed and eyes-open conditions, respectively (p < 0.05 uncorrected).

Figure 4:

Predictivity: correlation between the EEG-based vigilance time series and the estimated vigilance using matching and non-matching templates across different conditions. Left panel: 1- “EC→EC”: ECnonCaf template predicting vigilance fluctuations of the ECnonCaf scans, 2- “EO→EC”: EOnonCaf template predicting vigilance fluctuations of the ECnonCaf scans, 3- “EO→EO”: EOnonCaf template predicting vigilance fluctuations of the EOnonCaf scans, and 4- “EC→EO”: ECnonCaf template predicting vigilance fluctuations of the EOnonCaf scans. Right panel: comparing the predictivity before and after caffeine. Each symbol represents a subject and different scanning sessions are shown with different colors.

Figure 5:

Left: Relation between predictivity and the similarity between Temp_i and Temp_LOO for ECnonCaf (top) and EOnonCaf (bottom) scans. Top right: Individual templates (Temp_i) reshaped to 1-dimensional columns sorted based on the predictivity within each session, i.e. the subject on the left column in each session had the lowest predictivity and the subject on the rightmost column in each session had the highest predictivity. Bottom right: Predictivity values sorted within each session in blue and corresponding Temp_i magnitude values across subjects in green.

Figure 6:

Top row: Relation between the amplitude of the estimated vigilance time series (aVig_est) and the amplitude of the EEG-based vigilance time series (aVig) with the linear fit shown by the black lines. Bottom row: Relation between predictivity and the amplitude of the estimated vigilance time series (aVig_est) with the linear fit shown by the black lines.

Figure 7:

Predictivity using template versus the correlation between vigilance and global signal (inverted) for ECnonCaf and EOnonCaf conditions. The linear fits are shown by dark blue lines. The vertical, horizontal, and slanted black lines represent indicate the x-axis, y-axis, and line of unity, respectively.